1 files changed, 36 insertions, 32 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 9b301180fd41..a61a4407ebdf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -448,7 +448,7 @@ static bool vma_lock_alloc(struct vm_area_struct *vma)
 		return false;
 
 	init_rwsem(&vma->vm_lock->lock);
-	vma->vm_lock_seq = -1;
+	vma->vm_lock_seq = UINT_MAX;
 
 	return true;
 }
@@ -625,8 +625,8 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 	 * We depend on the oldmm having properly denied write access to the
 	 * exe_file already.
 	 */
-	if (exe_file && deny_write_access(exe_file))
-		pr_warn_once("deny_write_access() failed in %s\n", __func__);
+	if (exe_file && exe_file_deny_write_access(exe_file))
+		pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__);
 }
 
 #ifdef CONFIG_MMU
@@ -760,7 +760,8 @@ loop_out:
 		mt_set_in_rcu(vmi.mas.tree);
 		ksm_fork(mm, oldmm);
 		khugepaged_fork(mm, oldmm);
-	} else if (mpnt) {
+	} else {
+
 		/*
 		 * The entire maple tree has already been duplicated. If the
 		 * mmap duplication fails, mark the failure point with
@@ -768,8 +769,18 @@ loop_out:
 		 * stop releasing VMAs that have not been duplicated after this
 		 * point.
 		 */
-		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
-		mas_store(&vmi.mas, XA_ZERO_ENTRY);
+		if (mpnt) {
+			mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+			mas_store(&vmi.mas, XA_ZERO_ENTRY);
+			/* Avoid OOM iterating a broken tree */
+			set_bit(MMF_OOM_SKIP, &mm->flags);
+		}
+		/*
+		 * The mm_struct is going to exit, but the locks will be dropped
+		 * first.  Set the mm_struct as unstable is advisable as it is
+		 * not fully initialised.
+		 */
+		set_bit(MMF_UNSTABLE, &mm->flags);
 	}
 out:
 	mmap_write_unlock(mm);
@@ -1262,9 +1273,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
-#ifdef CONFIG_PER_VMA_LOCK
-	mm->mm_lock_seq = 0;
-#endif
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
@@ -1419,13 +1427,13 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 		 * We expect the caller (i.e., sys_execve) to already denied
 		 * write access, so this is unlikely to fail.
 		 */
-		if (unlikely(deny_write_access(new_exe_file)))
+		if (unlikely(exe_file_deny_write_access(new_exe_file)))
 			return -EACCES;
 		get_file(new_exe_file);
 	}
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
 	if (old_exe_file) {
-		allow_write_access(old_exe_file);
+		exe_file_allow_write_access(old_exe_file);
 		fput(old_exe_file);
 	}
 	return 0;
@@ -1466,7 +1474,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 			return ret;
 	}
 
-	ret = deny_write_access(new_exe_file);
+	ret = exe_file_deny_write_access(new_exe_file);
 	if (ret)
 		return -EACCES;
 	get_file(new_exe_file);
@@ -1478,7 +1486,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	mmap_write_unlock(mm);
 
 	if (old_exe_file) {
-		allow_write_access(old_exe_file);
+		exe_file_allow_write_access(old_exe_file);
 		fput(old_exe_file);
 	}
 	return 0;
@@ -1514,12 +1522,13 @@ struct file *get_task_exe_file(struct task_struct *task)
 	struct file *exe_file = NULL;
 	struct mm_struct *mm;
 
+	if (task->flags & PF_KTHREAD)
+		return NULL;
+
 	task_lock(task);
 	mm = task->mm;
-	if (mm) {
-		if (!(task->flags & PF_KTHREAD))
-			exe_file = get_mm_exe_file(mm);
-	}
+	if (mm)
+		exe_file = get_mm_exe_file(mm);
 	task_unlock(task);
 	return exe_file;
 }
@@ -1882,8 +1891,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_POSIX_TIMERS
 	INIT_HLIST_HEAD(&sig->posix_timers);
 	INIT_HLIST_HEAD(&sig->ignored_posix_timers);
-	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->real_timer.function = it_real_fn;
+	hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 #endif
 
 	task_lock(current->group_leader);
@@ -2023,25 +2031,18 @@ static inline void rcu_copy_process(struct task_struct *p)
  */
 static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	int pidfd;
 	struct file *pidfd_file;
 
-	pidfd = get_unused_fd_flags(O_CLOEXEC);
+	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
 	if (pidfd < 0)
 		return pidfd;
 
 	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
-	if (IS_ERR(pidfd_file)) {
-		put_unused_fd(pidfd);
+	if (IS_ERR(pidfd_file))
 		return PTR_ERR(pidfd_file);
-	}
-	/*
-	 * anon_inode_getfile() ignores everything outside of the
-	 * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
-	 */
-	pidfd_file->f_flags |= (flags & PIDFD_THREAD);
+
 	*ret = pidfd_file;
-	return pidfd;
+	return take_fd(pidfd);
 }
 
 /**
@@ -2423,8 +2424,11 @@ __latent_entropy struct task_struct *copy_process(
 	if (clone_flags & CLONE_PIDFD) {
 		int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
 
-		/* Note that no task has been attached to @pid yet. */
-		retval = __pidfd_prepare(pid, flags, &pidfile);
+		/*
+		 * Note that no task has been attached to @pid yet indicate
+		 * that via CLONE_PIDFD.
+		 */
+		retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;